arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.09352cs.CRcs.AI
收藏

通过未来恶意软件预测学习应对概念漂移

Counteracting Concept Drift by Learning with Future Malware Predictions

Avast Software(Avast软件公司);AI Center(人工智能中心);Czech Technical University in Prague(捷克技术大学布拉格分校)

Branislav Bosansky, Lada Hospodkova, Michal Najman, Maria Rigaki, Elnaz Babayeva, Viliam Lisy

AI总结:

针对恶意软件检测中的概念漂移问题,对比对抗训练与GAN两种未来样本预测方法,发现GAN可有效预测未来恶意软件并提升分类器在新数据上的准确率。

摘要:

由于数据分布的变化以及训练数据与测试数据之间差异的不断增大,已部署的恶意软件检测分类器的准确率会随时间下降,这种现象被称为概念漂移。虽然概念漂移通常可由多种原因引发,但恶意软件作者创建新的恶意文件时,有着明确的规避检测的意图,这种意图的存在为预测此类未来样本提供了可能性。将预测样本纳入训练数据,相应地应当能提升分类器在新测试数据上的准确率。\n 我们对比了两种预测未来样本的方法:(1)对抗训练,以及(2)生成对抗网络(GANs)。第一种方法会显式寻找针对分类器的对抗样本,随后将这些样本用作训练数据的一部分。与之类似,GANs 也能生成合成训练数据,我们利用 GANs 学习训练数据不同时间段内的数据分布变化,再应用这些变化生成可能出现在测试数据中的样本。我们在两个不同的数据集上对比了这些预测方法:(1)Ember 公开数据集,以及(2)Avast 接收文件的内部数据集。我们的研究表明,尽管对抗训练能得到鲁棒性更强的分类器,但总体而言该方法并非优秀的未来恶意软件预测手段,这与此前在自然语言处理、垃圾邮件检测等其他领域报道的积极结果形成对比。另一方面,我们证明 GANs 可成功用作未来恶意软件的预测工具。我们专门研究了数据分布随时间发生显著变化的恶意软件家族,实验结果证实,基于 GAN 的预测能显著提升分类器在全新的、此前未见过的数据上的准确率。

英文摘要:

The accuracy of deployed malware-detection classifiers degrades over time due to changes in data distributions and increasing discrepancies between training and testing data. This phenomenon is known as the concept drift. While the concept drift can be caused by various reasons in general, new malicious files are created by malware authors with a clear intention of avoiding detection. The existence of the intention opens a possibility for predicting such future samples. Including predicted samples in training data should consequently increase the accuracy of the classifiers on new testing data. We compare two methods for predicting future samples: (1) adversarial training and (2) generative adversarial networks (GANs). The first method explicitly seeks for adversarial examples against the classifier that are then used as a part of training data. Similarly, GANs also generate synthetic training data. We use GANs to learn changes in data distributions within different time periods of training data and then apply these changes to generate samples that could be in testing data. We compare these prediction methods on two different datasets: (1) Ember public dataset and (2) the internal dataset of files incoming to Avast. We show that while adversarial training yields more robust classifiers, this method is not a good predictor of future malware in general. This is in contrast with previously reported positive results in different domains (including natural language processing and spam detection). On the other hand, we show that GANs can be successfully used as predictors of future malware. We specifically examine malware families that exhibit significant changes in their data distributions over time and the experimental results confirm that GAN-based predictions can significantly improve the accuracy of the classifier on new, previously unseen data.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑